Industry-First Deployment of Humanoid Robots in Automotive Production Line
业界首个！具身智能实景实训示范落地，人形机器人开启产线“作业模式”
In October 2026, 15 humanoid robots from Leju Robotics and Zhao Feng Machinery began operating in a car parts production line in Zhejiang, marking the first replicable embodiment of intelligent training in real-world scenarios. The robots perform a sequence of 10+ actions with 98% success rate, collecting over 40,000 data points monthly. The project includes open-source contributions to the OpenLET community, aiming to lower industry R&D barriers and enable scalable deployment.
The article reports on the first industry-scale deployment of humanoid robots in a car parts production line, with 15 robots operating in a real-world setting. It highlights the integration of data collection, safety mechanisms, and open-source contributions to support broader industry adoption.
Source: Chinese robotics — Dataset and collection discovery · Read original article ↗
English translation unavailable. Choose the original article to read it.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
robot_count
15 robots
Reported trials
View original evidence
近日，乐聚机器人与兆丰机电在浙江联合发布“ 具身智能+汽车零部件上料解决方案” ，15台人形机器人在兆丰机电汽车零部件产线投入常态化运行。
Open source S2Reported success rate
98%
View original evidence
单次循环耗时40秒以内，适配15个工位、10余种零件，作业成功率稳定在98%，累计运行约1000小时，协助生产超过6万个零部件。
Open source S7running_time
≈1,000 hours
View original evidence
单次循环耗时40秒以内，适配15个工位、10余种零件，作业成功率稳定在98%，累计运行约1000小时，协助生产超过6万个零部件。
Open source S7components_produced
>60,000
View original evidence
单次循环耗时40秒以内，适配15个工位、10余种零件，作业成功率稳定在98%，累计运行约1000小时，协助生产超过6万个零部件。
Open source S7cycle_time
40 seconds
View original evidence
单次循环耗时40秒以内，适配15个工位、10余种零件，作业成功率稳定在98%，累计运行约1000小时，协助生产超过6万个零部件。
Open source S7action_sequences
>10
- dataset: not_reported
- code: not_reported
- weights: not_reported
- paper: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
近日，乐聚机器人与兆丰机电在浙江联合发布“ 具身智能+汽车零部件上料解决方案” ，15台人形机器人在兆丰机电汽车零部件产线投入常态化运行。
Open source S2
单次循环耗时40秒以内，适配15个工位、10余种零件，作业成功率稳定在98%，累计运行约1000小时，协助生产超过6万个零部件。
Open source S7
15台机器人同步作业，形成规模化并行数据采集能力，单月 可 采集超4万条 数据并 持续累积，机器人越用越“聪明”。
Open source S10
在兆丰产线，15台人形机器人在狭窄复杂环境中完成10余个动作序列，稳定抓取小型零件，打通“预备—取料—转运—上料”全流程。
Open source S6
Source：Chinese robotics — Dataset and collection discovery · tech.ifeng.com